@inproceedings{DoRehbeinFrank2018,
  author    = {Bich-Ngoc Do and Ines Rehbein and Anette Frank},
  title     = {What do we need to know about an unknown word when parsing German},
  series = {Proceedings of the First Workshop on Subword and Character Level Models in NLP (EMNLP 2017). September 7, 2017 Copenhagen, Denmark},
  publisher = {The Association for Computational Linguistics},
  address   = {Stroudsburg PA, USA},
  isbn      = {978-1-945626-91-3},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-80244},
  pages     = {117 -- 123},
  year      = {2018},
  abstract  = {We propose a new type of subword embedding designed to provide more information about unknown compounds, a major source for OOV words in German. We present an extrinsic evaluation where we use the compound embeddings as input to a neural dependency parser and compare the results to the ones obtained with other types of embeddings. Our evaluation shows that adding compound embeddings yields a significant improvement of 2\% LAS over using word embeddings when no POS information is available. When adding POS embeddings to the input, however, the effect levels out. This suggests that it is not the missing information about the semantics of the unknown words that causes problems for parsing German, but the lack of morphological information for unknown words. To augment our evaluation, we also test the new embeddings in a language modelling task that requires both syntactic and semantic information.},
  language  = {en}
}